© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6680
    Prev
    Next
    INDEX
    Explanations

    closing signature with options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    т
    1.64
    ्स
    1.43
    y
    1.29
    s
    1.22
     gehör
    1.17
    сто
    1.15
    ת
    1.15
    ן
    1.14
    yiz
    1.13
    ″
    1.13
    POSITIVE LOGITS
     बेसब्री
    1.21
     encarg
    1.13
    𝐀
    1.12
     Marilyn
    1.10
     dietitian
    1.10
     viscos
    1.09
     aldehydes
    1.09
    渽
    1.07
     happier
    1.05
    addPreferred
    1.05
    Activations Density 0.017%

    No Known Activations